SOTAVerified

Class Incremental Learning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 176–200 of 634 papers

TitleStatusHype
Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning—0
Multi-label Class Incremental Emotion Decoding with Augmented Emotional Semantics Learning—0
Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond—0
Recent Advances of Foundation Language Models-based Continual Learning: A Survey—0
Compositional Few-Shot Class-Incremental LearningCode0
Few-shot Tuning of Foundation Models for Class-incremental LearningCode0
On Sequential Loss Approximation for Continual LearningCode0
Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning PerspectiveCode0
Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental LearningCode1
Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory—0
Mitigating Interference in the Knowledge Continuum through Attention-Guided Incremental LearningCode0
FeTT: Continual Class Incremental Learning via Feature Transformation Tuning—0
Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning—0
Dynamic Feature Learning and Matching for Class-Incremental Learning—0
Feature Expansion and enhanced Compression for Class Incremental LearningCode0
Few-Shot Class Incremental Learning via Robust Transformer ApproachCode0
Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning—0
Continual Learning in the Presence of Repetition—0
FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer—0
Few Shot Class Incremental Learning using Vision-Language models—0
Hard ASH: Sparsity and the right optimizer make a continual learner—0
Revisiting Neural Networks for Continual Learning: An Architectural PerspectiveCode1
Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental Learning—0
DynaMMo: Dynamic Model Merging for Efficient Class Incremental Learning for Medical ImagesCode0
Realistic Continual Learning Approach using Pre-trained Models—0
Show:102550
← PrevPage 8 of 26Next →
All datasetscifar100CIFAR-100 - 50 classes + 10 steps of 5 classesCIFAR-100 - 50 classes + 5 steps of 10 classesCifar100-B0(10 tasks)-no-exemplarsCifar100-B0(20 tasks)-no-exemplarsCIFAR100-B0(50 tasks)-no-exemplars

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1S&B10-stage average accuracy68.18—Unverified
2SCR10-stage average accuracy65.98—Unverified
3iCaRL10-stage average accuracy63.24—Unverified
4LUCIR10-stage average accuracy56.53—Unverified
5ABD10-stage average accuracy54.44—Unverified
6EWC10-stage average accuracy50.53—Unverified
7EMR10-stage average accuracy48.66—Unverified
8A-GEM10-stage average accuracy45.76—Unverified
#ModelMetricClaimedVerifiedStatus
1PPCA-SWSLFinal Accuracy77.07—Unverified
2PPCA-CLIPFinal Accuracy69.71—Unverified
#ModelMetricClaimedVerifiedStatus
1PPCA-SWSLFinal Accuracy77.07—Unverified
2PPCA-CLIPFinal Accuracy69.71—Unverified
#ModelMetricClaimedVerifiedStatus
1SEEDAverage Incremental Accuracy61.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SEEDAverage Incremental Accuracy56.2—Unverified
#ModelMetricClaimedVerifiedStatus
1SEEDAverage Incremental Accuracy42.6—Unverified